I am an Insight Analyst at Etraveli in Uppsala, Sweden, and an Affiliate Researcher at the Department of Linguistics and Philology of Uppsala University.
My research focuses on computational historical linguistics, particularly developing methods for analyzing the evolution of languages and text traditions. I specialize in phylogenetic methods that facilitate the use of phonological information in linguistic phylogenetics, from sound correspondences to inferences of sound changes.
In my current work, I tackle complex business problems by combining my research background with practical data analysis. This means diving deep into large databases to understand what’s really going on, building machine learning models to predict operational issues before they happen, and investigating why customers are dissatisfied or where processes are breaking down. I spend a lot of time exploring data quality issues, uncovering root causes in ambiguous situations, and translating messy real-world problems into clear analytical questions. The computational methods I developed for linguistics research (like working with large-scale structured data, detecting patterns, and validating hypotheses rigorously) turn out to be surprisingly useful when you’re trying to figure out why a booking system is failing or what’s driving customer support contacts.
I love programming, primarily using Python but also exploring R and C. My Ph.D. thesis examined the classical as a means of relationship with otherness, as showcased by the literary development of Odysseus. Which is fitting, I suppose, since I’ve been wandering between disciplines ever since: literature to linguistics to data science, still not quite sure if I’m heading back to Ithaca or just circling. Let’s hope I don’t end up like Dante’s Ulysses, sailing past the pillars and into the abyss for the sake of one more intellectual adventure.
Current Projects
- Arca Verborum: Large-scale lexical database for computational historical linguistics (project page)
- PhyloVector: Vector-based approaches to phylogenetic analysis
- Uralic phylogeny: Computational methods for Uralic language relationships
- Arawan family: South American language family analysis
- Tafl games: Computer game programming with chess-inspired algorithms
Recent Work
Check my blog for thoughts on linguistics, data science, LLMs, and academic life, or explore my research, software, and LLM work projects.